Questions about PyTorch version

[wwq66]

Why should the Pytorch version be 0.3 ? Problems occur when using PyTorch 0.3. What's more, .item() and with torch.no_grad(): should be used in version 0.4 and higher.

[habout632]

Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method

[habout632]

problem occurs when loading data

[rajendrac3]

Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method

To resolve this: Change 'self.num_workers = 4' to 'self.num_workers = 0' at line 22 in dataloader.py